AMR-to-Text Generation via GF Normunds Grztis University of - - PowerPoint PPT Presentation
AMR-to-Text Generation via GF Normunds Grztis University of Latvia, Institute of Mathematics and Computer Science National information agency LETA GF Summer School 2017, Rga, Latvia This work has received funding in part from the
Normunds Grūzītis
University of Latvia, Institute of Mathematics and Computer Science National information agency LETA
GF Summer School 2017, Rīga, Latvia
This work has received funding in part from the Latvian State research programs SOPHIS and NexIT, the EU Horizon 2020 project SUMMA (grant No. 688139), and the European Regional Development Fund (grant No. 1.1.1.1/16/A/219).
– FrameNet – PropBank
– SemEval 2016 – SemEval 2017
TurboParser + SEMAFOR: http://demo.ark.cs.cmu.edu/parse FrameNet LTH parser: http://barbar.cs.lth.se:8081/ PropBank
– A semantic frame represents a cognitive, prototypical situation (scenario) characterized by frame elements (FE) – semantic valence – Frames are “evoked” in sentences by target words – lexical units (LU) – FEs are mapped based on the syntactic valence of the LU
(for an increasing number of languages, incl. Latvian)
– FEs are split into core and non-core ones
correspond to verb arguments
want.v..6412 känna_för.vb..1 Introduced in BFN, reused in SweFN
e.g. “[I]Experiencer do n't WANT [to deceive anyone]Event” | an embedded frame
Some valence patterns found in SweFN Some valence patterns found in BFN
e.g. “[Jag]Experiencer KÄNNER FÖR [en tur på landet]Focal_participant”
– A limited but computational FN-based GF grammar and lexicon
– Separates between an abstract syntax and concrete syntaxes – Provides a general-purpose resource grammar library (RGL)
the abstract syntax
– The language-specific layers (surface realization of frames and FEs; LUs) – concrete syntaxes
FNs and for the concrete implementation of frames
– FrameNet allows for abstracting over RGL
– In combination with the syntactic API of RGL – Hiding the comparatively complex construction of verb phrases
mkCl person (mkVP (mkVP live_V) (mkAdv in_Prep place))
Residence
person
(mkAdv in_Prep place) -- Adv (Location) live_V_Residence
Imants Ziedonis ir dzimis 1933. gada 3. maijā Slokas pagastā. Imants Ziedonis was born in Sloka parish on 3 May 1933.
– Taking one or more core FEs (A-Z) and one LU as arguments – Returning an object of type Clause whose linearization type is
{np: NP; vp: VP}
– NP, VP, Adv (includes prepositional objects), S (embedded sentences), QS
cat Event_VP cat Focal_participant_NP cat Experiencer_NP cat Focal_participant_Adv fun Desiring_V : Experiencer_NP -> Focal_participant_Adv -> V -> Clause fun Desiring_V2 : Experiencer_NP -> Focal_participant_NP -> V2 -> Clause fun Desiring_V2_Pass : Experiencer_NP -> Focal_participant_NP -> V2 -> Clause fun Desiring_VV : Event_VP -> Experiencer_NP -> VV -> Clause
types is shared for all languages
– Linearization types are of type Maybe to allow for optional (empty) FEs
arguments depending on their types and syntactic roles, and the voice
lincat Focal_participant_NP = Maybe NP lincat Focal_participant_Adv = Maybe Adv lin Desiring_V2 experiencer focal_participant v2 = { np = fromMaybe NP experiencer ; vp = mkVP v2 (fromMaybe NP focal_participant) } lin Desiring_V2_Pass experiencer focal_participant v2 = { np = fromMaybe NP focal_participant ; vp = mkVP (passiveVP v2) (mkAdv by8agent_Prep (fromMaybe NP experiencer)) }
http://grammaticalframework.org/framenet/
TurboParser + SEMAFOR: http://demo.ark.cs.cmu.edu/parse FrameNet LTH parser: http://barbar.cs.lth.se:8081/ PropBank
– Incl. PropBank SRL, NER and NEL, treatment of modality, negation, etc.
– PENMAN notation: directed labeled graph encoded in a tree-like form – Easy to read and write (for a human), and traverse (for a program) – Langkilde and Knight (1998) à Banarescu et al. (2013)
– Practical, replicable amount of abstraction – An actual sembank of 40K+ sentences
– Aims to abstract away from (English) syntax
– Entities, events, states, properties – s / soldier: s is an instance of soldier
f / fear-01 d / die-01 s / soldier
ARG1
(Pust et al., 2015)
Schneider N., Flanigan J., O’Gorman T. AMR Tutorial at NAACL 2015 https://github.com/nschneid/amr-tutorial/
towards English or other source languages
agnostic about how to derive meanings from strings, and vice versa
Palmer M., Uresova Z., Zhang X. Not an Interlingua, but close: Comparison of English AMRs to Chinese and
https://amr.isi.edu/editor.html
# ::snt A fourth member, Jean-Marc Rouillan, remains behind bars.
(r / remain-01 :ARG1 (p / person :wiki - :name (n / name :op1 "Jean-Marc" :op2 "Rouillan") :mod (p2 / person :ARG0-of (h / have-org-role-91 :ARG2 (m / member)) :ord (o / ordinal-entity :value 4))) :ARG3 (b / behind :op1 (b2 / bar)))
# ::snt A fourth member, Jean-Marc Rouillan, remains behind bars.
(r / remain-01 :ARG1 (p / person :wiki - :name (n / name :op1 "Jean-Marc" :op2 "Rouillan") :mod (p2 / person :ARG0-of (h / have-org-role-91 :ARG2 (m / member)) :ord (o / ordinal-entity :value 4))) :ARG3 (b / behind :op1 (b2 / bar)))
Remaining members person 4 jean-marc rouillan – behind bar. Jean-Marc Rouillan, that is the 4th member, is remained behind a bar.
# ::snt A fourth member, Jean-Marc Rouillan, remains behind bars.
(r / remain-01 :ARG1 (p / person :wiki - :name (n / name :op1 "Jean-Marc" :op2 "Rouillan") :mod (p2 / person :ARG0-of (h / have-org-role-91 :ARG2 (m / member)) :ord (o / ordinal-entity :value 4))) :ARG3 (b / behind :op1 (b2 / bar)))
Remaining members person 4 jean-marc rouillan – behind bar. JAMR Jean-Marc Rouillan, that is the 4th member, is remained behind a bar. GF
# ::snt A fourth member, Jean-Marc Rouillan, remains behind bars.
(r / remain-01 :ARG1 (p / person :wiki - :name (n / name :op1 "Jean-Marc" :op2 "Rouillan") :mod (p2 / person :ARG0-of (h / have-org-role-91 :ARG2 (m / member)) :ord (o / ordinal-entity :value 4))) :ARG3 (b / behind :op1 (b2 / bar)))
Remaining members person 4 jean-marc rouillan – behind bar. JAMR Jean-Marc Rouillan, that is the 4th member, is remained behind a bar. GF
# ::snt They should have been expelled from school at a minimum.
(r / recommend-01 :ARG1 (e / expel-01 :ARG1 (t / they) :ARG2 (s / school) :degree (a / at-a-minimum)))
Should they at-a-minimum expel school. JAMR It is recommended that they are expelled to a school at a minimum. GF
expel-01 ARG0=PAG (prototypical agent) ARG1=PPT (prototypical patient) ARG2=DIR (direction) à DIR_Prep à to_Prep
ToDo: based on statistics from PropBank and FrameNet corpora, “reconstruct” Prep-s, depending on frame/verb valency, ARG role, or NP head
# ::snt Texas criminal courts and prosecutors do not coddle to anyone. (c / coddle-01 :polarity – :ARG0 (a / and :op1 (c2 / court :ARG0-of (c4 / criminal-03) :location (s / state :wiki "Texas" :name (n / name :op1 "Texas"))) :op2 (p / person :ARG0-of (p2 / prosecute-01) :location s)) :ARG1 (a2 / anyone)) No texas texas criminal court and prosecutors coddle anyone. JAMR A criminal court in Texas and a person that prosecutes do not coddle anyone. GF
person that prosecutes à prosecutor
# ::snt How Long are We Going to Tolerate Japan?
(t / tolerate-01 :ARG0 (w / we) :ARG1 (c / country :wiki "Japan" :name (n / name :op1 "Japan")) :duration (a / amr-unknown))
We have tolerated the japan amr-unknown. JAMR How long do we tolerate Japan? GF
if ':mode expressive' in amr: amr = amr.replace(':mode expressive', ' ') + ' !' if ':mode imperative' in amr: amr = amr.replace(':mode imperative', ' ') + ' !' if ':mode interrogative' in amr: amr = amr.replace(':mode interrogative', ' ') + ' ?' if 'cause-01:ARG0(amr-unknown)' in amr: amr = 'why ' + amr.replace('cause-01:ARG0(amr-unknown)', ' ') + ' ?' if ':location(amr-unknown)' in amr: amr = 'where ' + amr.replace(':location(amr-unknown)', ' ') + ' ?' if ':ARG1(amr-unknown)' in amr: amr = 'who ' + amr.replace(':ARG1(amr-unknown)', ' ') + ' ?' if ':mod(amr-unknown)' in amr: amr = 'what ' + amr.replace(':mod(amr-unknown)', ' ') + ' ?' if ':duration(amr-unknown)' in amr: amr = 'how ' + amr.replace(':duration(amr-unknown)', ' ') + ' ?' if 'amr-unknown' in amr: amr = 'what ' + amr.replace('amr-unknown', ' ') + ' ?'
# ::snt Xinhua News Agency, Tokyo, September 1st, by reporter Yiguo Yu
(b / byline-91 :ARG0 (p2 / publication :name (n / name :op1 "Xinhua" :op2 "News" :op3 "Agency")) :ARG1 (p / person :name (n2 / name :op1 "Yiguo" :op2 "Yu") :ARG0-of (r / report-01)) :location (c2 / city :name (n3 / name :op1 "Tokyo")) :time (d / date-entity :month 9 :day 1))
Xinhua news agency has reported yiguo yu byline in a tokyo 1 9. JAMR Xinhua News Agency by Yiguo Yu on 1 September in Tokyo. GF
# ::snt Alliot-Marie arrived on Sunday.
(a / arrive-01 :ARG1 (p / person :name (n / name :op1 "Alliot-Marie")) :time (d / date-entity :weekday (s / sunday)))
Sunday 's arrival of alliot-marie michèle_alliot-marie. JAMR
unknown qualified constant L.arrive_V2
GF
(a / arrive-01 :ARG0 (p / person :name (n / name :op1 "Alliot-Marie")) :time (d / date-entity :weekday (s / sunday))) Alliot-marie michèle_alliot-marie arrived sunday. JAMR Alliot-Marie arrives on Sunday. GF
JAMR (5-grams) AMRà(U)Dàlin UL / IMCS / LETA Tranducer à lin SMT: AMR à Eng Approaches:
SemEval ACL
“We made the following resources available to participants: [..] The JAMR (Flanigan et al., 2016) generation system, as a strong generation baseline. [..]” (May & Priyadarshi, 2017)
à à à
# mkVP : VV -> VP -> VP # (frame1 (:ARG1 (var frame2))) => (frame1 (mkVP frame2)) /VV_FRAME/ < (/:ARG1/=vp < (/VAR/=var < /FRAME/=v)) # Tregex [move v >1 vp] [relabel vp /^.+$/mkVP/] [delete var] # Tsurgeon
representations for machine translation. NAACL Workshop on Semantics-Driven Machine Translation, 2016
TestTrees: t01_girls_see_a_boy TestTreesEng: a girl sees a boy . TestTreesLav: meitene redz zēnu . TestTreesRus: девочка видит мальчика . TestTrees: t04_two_pretty_girls_see_a_boy TestTreesEng: 2 pretty girls see a boy . TestTreesLav: 2 jaukas meitenes redz zēnu . TestTreesRus: 2 хорошенькие девочки видят мальчика . TestTrees: t21_girls_who_see_the_game_like_the_boys_who_play TestTreesEng: a girl that sees a game likes a boy that plays . TestTreesLav: meitenei , kas redz spēli , patīk zēns , kas spēlē . TestTreesRus: девочка , которая видит игру нравдит мальчика , которого играет . TestTrees: t27_they_are_thugs_and_deserve_a_bullet TestTreesEng: they are a thug and it deserves a bullet . TestTreesLav: viņi ir slepkava , un pelna lodi .
1. The input AMR is rewritten from the PENMAN notation to the the LISP-like bracketing tree syntax. 2. In case of a multi-sentence AMR, the graph is split into two or more graphs to be processed separately. 3. For each AMR, a sequence of tree pattern-matching transformation rules is applied (Tregex + Tsurgeon), acquiring a fully or partially converted GF abstract syntax tree (AST). 4. In case of a partially converted AST, the pending subtrees are pruned.** 5. The resulting ASTs are passed to the GF interpreter for RGL-based linearization. 6. Since RGL supports many more languages (30+), this approach can be extended to multilingual AMR-to-text generation, given a large translation lexicon (15+).
** Our SemEval submission:
Because the coverage of our hand-crafted AMR-to-AST transformation rules is currently far from complete, we used JAMR Generator (Flanigan et al., 2016) as a “fall-back” option for AMRs that are not fully covered by the current rule set (~200). However, we applied heuristic post-processing rules to the JAMR output, which might have influenced the human judgements:
constructs.
BBC monitoring journalists translate from 30 languages into English, follow 400 social media accounts every day. A monitoring journalist typically monitors 4 TV channels and several online sources
sources. Monitoring journalists constantly need to be on the lookout for more sources and follow important stories—but as it is, they are tied down with mundane, routine monitoring tasks. Monitoring 250 video channels results in a daily buffer of 2.5TB, a weekly buffer of 19Tb, and an annual buffer of 1Pb.
Identify people, places, events of interest Discover trends, emerging events, crucial new stories
H2020 grant No. 688139
selects representative sentences from the input documents
builds a semantic representation from which a summary is generated
representation?
– PropBank / FrameNet – AMR
Sentence A: I saw Joe’s dog, which was running in the garden. Sentence B: The dog was chasing a cat. Summary: Joe’s dog was chasing a cat in the garden.
Liu F., Flanigan J., Thomson S., Sadeh N., Smith N.A. Toward Abstractive Summarization Using Semantic Representations. NAACL 2015
0.6195
* Rule/grammar-based; did not use AMR training data
– SemEval 2016: few grammar-based systems – SemEval 2017: no grammar-based systems (Boxer gave up…)
– Add more Tregex/Tsurgeon rules – A more flexible and systematic graph/tree-transducer (like UD2GF) – Learning transformation rules (C6.0; training data?) – Seq-to-seq deep learning?
for GF. CNL 2012
FrameNet-annotated corpora. LREC 2014
multilingual FrameNet-based grammar. CNL 2014
Swedish Constructicon in Grammatical Framework. GEAF 2015
summarization for multilingual media monitoring. CNL 2016
for Controlled Natural Language. Language Resources and Evaluation, 51(1), 2017
Combining Machine Learning and Grammar Engineering for AMR Parsing and